INDEX

Explanations

references to specific names or entities, particularly in technical or formal contexts

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k

Configuration

google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73

Prompts (Dashboard)

36,864 prompts, 128 tokens each

Dataset (Dashboard)

monology/pile-uncopyrighted

Features

16,384

Data Type

float32

Hook Name

blocks.19.hook_resid_post

Hook Layer

Architecture

jumprelu

Context Size

1,024

Dataset

monology/pile-uncopyrighted

Activation Function

relu

Embeds

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

 فريبيس

-1.07

Diweddarwch

-0.85

 otomatig

-0.85

 المعيارى

-0.84

 Bourgoin

-0.78

RetentionPolicy

-0.77

 GenerationType

-0.75

IContainer

-0.72

Distribuzione

-0.72

 MediatR

-0.71

POSITIVE LOGITS

 however

0.79

 though

0.76

However

0.72

 nevertheless

0.70

 also

0.69

 notwithstanding

0.66

Nevertheless

0.65

 although

0.64

 However

0.64

however

0.62

Activations Density 0.260%

references to specific names or entities, particularly in technical or formal contexts

No Comments

No Known Activations